Frequently asked questions
Is the AI voice over completely free?
You start with a free trial of $0.50 credit, valid for seven days, when signing in with Google. After that, usage costs $0.01 per 1,000 characters. Failed requests are free, and your balance never expires. There are no monthly plans or minimum spends, so you only pay for what you generate.
Can I use this audio for monetized YouTube videos?
Yes, the generated audio is royalty-free. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. You can use the audio in your monetized YouTube videos without additional licensing fees, as the input text is not used for training.
Which voices sound the most natural?
Naturalness is subjective, but we offer eight presets like Aria (warm narrator), Nova (bright, upbeat), and Atlas (neutral, news). All voices are based on licensed recordings from LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. You can test all voices via the /v1/voices endpoint.
How many languages are supported?
We support 23 languages, including English, Spanish, French, German, Japanese, and Chinese. Any voice can speak any of these languages. If you do not set the language, it guesses from the script, defaulting to English for Latin text. Vietnamese, Thai, and Ukrainian are not supported.
Do I need to install any software?
No. This is a cloud API. You send text via a POST request to our endpoint and receive an audio file. You can use the official OpenAI SDKs by changing the base URL, or use plain HTTP. No mobile SDKs, WordPress plugins, or local installations are required.
What happens if my request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry your request using the same API key and parameters without any additional cost or penalty.
Is there a limit on video length?
There is no direct limit on video length, but each API request accepts up to 4,096 characters. For longer scripts, split the text into parts, generate each, and join the audio files. Typical speed is roughly real-time, so long videos will take time to process sequentially.
Can I change the speed of the voice?
Yes, you can adjust the speed between 0.25 and 4.0. This allows you to make the voice faster for quick updates or slower for detailed explanations. The speed parameter is part of the standard request body, working alongside the model, voice, and input text fields.
Are the voices copyrighted?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. The generated audio files are royalty-free for your use. While the source material has specific licenses, the output is yours to use in your projects without further restriction.
Do I need to credit the AI voice?
The source recordings are under CC BY 4.0 or public domain. While attribution is good practice, our API output is royalty-free. We do not mandate specific credit lines for the synthetic speech in your videos. However, check the original LibriVox licenses if you use the raw source files.
How fast is the generation process?
Typical speed is roughly real-time, generating about 25 characters of text per second of audio. Short phrases take a few seconds. Requests are processed sequentially, so under load, your request may wait in a queue. Longer texts will take proportionally longer to synthesize and return.
Can I use multiple voices in one video?
Yes. Generate each segment with the desired voice using separate API requests. Then, join the resulting audio files. You can mix voices like Aria, Felix, or Atlas within a single video project. This gives you full control over the narrative flow and character distinctness.
Is there a character limit per request?
Yes, each request accepts up to 4,096 characters. Spaces and punctuation count toward this limit. For longer content, split your text into chunks of 4,096 characters or less, generate the audio for each, and concatenate the files to create your final video audio track.
How do I pay if I run out of credit?
Top up using USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or subscriptions. Your balance never expires, and you can issue a new API key anytime if needed.
First request
curl
curl https://api.heng9999th.com/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why Creators Choose Our Free AI Voice Generator
Turn blog posts and scripts into natural-sounding audio without worrying about royalty disputes. Our API generates royalty-free speech, so you can monetize your YouTube videos with confidence. Focus on editing, not recording.
We keep things simple: no hidden fees, no subscriptions, and no minimum spend. You only pay for what you use, making it easy for freelancers to manage their budgets.
Royalty-free audio for YouTube monetization
Every generated file is yours to use commercially. Since the voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings, you get clean audio ready for your channel.
- No recurring licensing fees
No hidden fees or subscriptions
Start with a $0.50 free trial when you sign in with Google. Top up with USDT only when you need more characters. Balance never expires.
Instant API access for bulk generation
Get your API key immediately after signing up. Use the standard OpenAI-compatible endpoint to automate your workflow and generate audio in bulk without manual clicks.
You can send up to 4096 characters per request, making it easy to script long-form content efficiently.
- POST https://api.heng9999th.com/v1/audio/speech
- Standard JSON body format
How It Works: From Script to Speech
Turn your YouTube scripts, blog posts, or rough notes into natural-sounding audio in minutes. Our API handles the heavy lifting, so you can focus on editing rather than recording. Simply paste your text, select your preferred voice and language, and receive the audio file ready for your video.
Whether you are creating faceless channel content or video essays, the process is straightforward. Generate high-quality speech without hiring voice actors or buying expensive software. Start with a free trial and scale as your channel grows.
Paste your YouTube script
Copy your script, whether it is a 5-minute video essay or a 40-character hook. The API accepts up to 4096 characters per request, making it easy to process standard YouTube segments. If your script is longer, split it into parts and join the resulting audio files seamlessly.
- Supports plain text, blog posts, and rough notes
- Handles up to 4096 characters per request
- Splits long texts into parts and joins the resulting audio files
Choose a voice and language
Select from eight distinct voice presets like Aria for warm narration or Felix for energetic promos. The system supports 23 languages, including English, Spanish, Japanese, and Korean. You can specify a language code or let the API guess it based on your script's script.
- 8 presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion
- 23 languages supported globally
- Adjustable speed from 0.25x to 4.0x
Download your audio file
Receive your audio file instantly in your preferred format: MP3, WAV, OPUS, FLAC, or PCM. The generated speech carries an inaudible watermark to identify it as synthetic, ensuring clear rights for your YouTube monetization. Upload directly to your video editor without further processing.
- Formats: MP3, WAV, OPUS, FLAC, PCM
- Inaudible synthetic watermark included
- Royalty-free for YouTube content
Voices That Match Your Content Style
Selecting the right voice defines your channel's identity. Our eight presets are designed for clarity and natural rhythm. Whether you need a warm companion or a neutral news anchor, the right tone is just a parameter away.
Warm narrators like Aria and Luna
Aria delivers clear, warm narration ideal for book reviews or personal vlogs. Luna adds a soft, storytelling quality perfect for emotional or narrative-driven content.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling
Energetic promos with Felix
Felix brings high energy to promotional clips, product reviews, or fast-paced YouTube shorts. His tone keeps viewers engaged and excited about your content.
- Felix: Energetic, promo
Calm storytelling with Sage and Orion
Sage offers a calm, instructional voice for tutorials and how-to guides. Orion provides a deep, documentary-style tone for video essays and serious topics.
- Sage: Calm, instructional
- Orion: Deep, documentary
23 Languages for Global Reach
Generate natural-sounding narration in 23 languages, allowing you to repurpose existing scripts for global audiences without hiring separate voice actors. Our API supports accurate pronunciation across diverse linguistic families, ensuring your content resonates with viewers from different regions.
English, Spanish, and French
Start with the most widely spoken languages in content creation. Use Aria for clear, warm narration in English, or Luna for softer storytelling in French. Spanish support allows you to reach Latin American and European markets with the same high-quality engine.
- Native-like clarity for major Western markets
- Consistent voice quality across all supported dialects
Asian languages including Japanese and Korean
Expand into high-growth markets with precise tonal accuracy. Our engine handles Japanese and Korean, ensuring that intonations sound natural. This is essential for maintaining viewer retention in these competitive niches.
- Accurate tone handling for Japanese
- Natural flow for Korean speech patterns
European and African languages supported
Diversify your reach with languages like German, Italian, Swahili, and Turkish. Whether you are creating documentary-style content or educational tutorials, you can now produce audio in these regions without leaving the platform. Each voice maintains its distinct character across all supported languages.
- Support for 23 distinct languages
- No additional cost for multi-language content
Pricing Built for Freelancers
Our pricing is straightforward: $0.01 per 1,000 characters. Failed requests are free, so you never pay for errors. You can top up with USDT on the TRON network, starting at just $5. There are no monthly subscriptions, no seats to manage, and no minimum spend requirements.
This model lets you scale your voice-over production exactly as your content grows. Whether you are generating a short clip or a long documentary, you only pay for the characters you actually use. Balances do not expire, giving you flexibility for your workflow.
$0.01 per 1,000 characters
The cost is simple and predictable. You pay $0.01 for every 1,000 characters processed, including spaces and punctuation. If a synthesis fails, the charge is returned in full.
Longer texts are split into parts of up to 4096 characters and joined seamlessly. This ensures consistent quality without hidden volume discounts or complex tiers.
- No minimum spend or monthly subscriptions
- Failed requests are free
- Spaces and punctuation count as characters
Free trial with $0.50 credit
Sign up with Google to receive $0.50 of credit, which covers approximately 50,000 characters. This trial is valid for 7 days, giving you plenty of time to test the API quality. Accounts created with email and password do not receive this trial credit.
This allows you to verify that the voices match your YouTube content style before committing to larger batches of generation.
Pay only what you use
Top-ups are made via USDT on the TRON network (TRC-20). Transfers are credited automatically within minutes, so you can start generating immediately. There are no invoices with VAT or complex billing cycles to track.
Your balance never expires. You can top up whenever it suits your production schedule, ensuring you always have credits ready for your next video upload.
Technical Specs for Developers
Drop our API endpoint into your existing OpenAI SDK configuration by changing the base URL to https://api.heng9999th.com/v1. You can then use standard libraries like the official Python or Node.js OpenAI SDKs without writing custom HTTP clients, simply swapping the key and endpoint.
OpenAI-compatible API endpoint
Use the standard POST /v1/audio/speech endpoint with the same JSON body structure as OpenAI. Simply point your SDK's base_url to https://api.heng9999th.com/v1 and provide your tts-... bearer token. This allows you to use familiar OpenAI SDKs with zero code changes for request shaping.
- Endpoint:
POST https://api.heng9999th.com/v1/audio/speech - Auth:
Authorization: Bearer tts-... - SDKs: Compatible with official OpenAI libraries
Support for MP3, WAV, and FLAC
Generate audio in MP3, WAV, OPUS, FLAC, or PCM formats using the response_format parameter. MP3 offers efficient file sizes for web streaming, while WAV and FLAC provide lossless quality for professional editing workflows. Choose the format that best fits your YouTube upload requirements.
- Formats: mp3, wav, opus, flac, pcm
- Optimized for web and editing
Rate limits of 60 requests per minute
The API allows 60 requests per minute per key, enabling efficient bulk processing for longer scripts. For high-volume needs, split texts into 4096-character chunks and process them sequentially. Note that processing is sequential, so under heavy load, requests may queue briefly.
- Limit: 60 requests/minute/key
- Pre-top-up limit: 10 requests/minute
Common Use Cases for YouTube
Turn blog posts or scripts into natural-sounding audio for your YouTube channel. Our API lets you generate royalty-free speech in 23 languages, so you can focus on editing rather than recording.
Faceless channel narration
Generate consistent voiceovers for facts, news, or story channels without appearing on camera. Use voices like Aria for clear narration or Atlas for neutral delivery.
- Ideal for compilation or commentary channels
- Maintain consistent audio quality across videos
Video essay voiceovers
Add depth to your analysis with warm, storytelling tones. Sage offers a calm, instructional style perfect for deep dives, while Orion provides a deep, documentary feel.
- Supports long scripts split into 4096-character chunks
- Royalty-free audio for monetization
Tutorial and explainer videos
Clarify complex topics with clear, upbeat voices like Nova or friendly tones from Milo. Keep your audience engaged with precise, natural-sounding instructions.
- Fast generation for quick turnaround
- Supports multiple languages for global tutorials
Data Privacy and Rights
Your creative control matters when building a channel. We respect your intellectual property by keeping your input text strictly for the sole purpose of generating the audio file. It is not added to any training datasets, ensuring your unique scripts remain yours.
Input text is not used for training
Unlike some consumer-grade services, we do not use your raw text to train our models. Your blog posts, scripts, and notes are processed once and then discarded from any learning pool, preserving your original content's value.
Audio files are returned instantly
Synthesized audio is delivered directly in the API response and is not stored on our servers for extended periods. You receive the file immediately, ready for download and integration into your editing workflow without waiting for cloud retrieval processes.
No storage of your generated content
While we keep basic metadata (time, characters, status) for accurate billing, the generated audio files themselves are not retained. This minimizes data exposure and ensures your final voiceovers are not sitting in a database you didn't ask to keep.
Get Started with Your First Voice Over
Start your YouTube voiceover workflow by signing up with Google to receive an immediate $0.50 trial credit. This gives you approximately 50,000 characters of free generation for seven days, with no credit card required. Access your API key instantly on the dashboard to begin testing.
Sign up with Google for instant credit
Create an account at /get-api-key/ using your Google identity. You receive $0.50 in trial credit valid for 7 days, allowing you to test the API without upfront payment. Email sign-ups do not include this trial credit.
Generate approximately 50,000 characters
Use your API key to send text to the endpoint. You can generate approximately 50,000 characters during your trial period. Split longer scripts into chunks under 4,096 characters and join the resulting audio files manually.
Export and upload to YouTube
Download the returned audio file in your preferred format (MP3, WAV, Opus, FLAC, or PCM). Since the output is royalty-free synthetic speech, you can directly upload it to your YouTube videos for monetization without copyright strikes.
- Supported formats: MP3, WAV, Opus, FLAC, PCM
- No copyright claims on generated synthetic audio
- Works with standard YouTube upload workflows
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.